nwpie/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2026-02-05 13:53:23 +02:00
Code Issues Packages Projects Releases Wiki Activity
7,948 Commits 540 Branches 5,431 Tags

Default Branch

master

b828e18c75 · docker : fix vulkan build (#19352) · Updated 2026-02-05 12:10:39 +02:00
 ZIP  TAR.GZ

Branches

0cc4m/vulkan-fa-scalar-opt

affe132f53 · use row_split when Br >= 4, change reductions to use shared memory if row_split == 1 · Updated 2026-02-05 13:51:59 +02:00
41
3
 ZIP  TAR.GZ
gg/metal-fa-mask-zero-opt

fd56915a9d · cont : minor · Updated 2026-02-05 10:11:27 +02:00
11
2
 ZIP  TAR.GZ
gg/spec-disable-for-recurrent

46c3bb1691 · spec : check if the target context is compatible for spec decoding · Updated 2026-02-04 13:20:35 +02:00
39
3
 ZIP  TAR.GZ
gg/ci-server-add-metal

8479be0ee5 · cont : try fix python init · Updated 2026-02-04 12:55:19 +02:00
40
4
 ZIP  TAR.GZ
gg/qwen3next-fix-chunking

1213a03564 · qwen3next : fix chunking · Updated 2026-02-04 10:06:38 +02:00
16
1
 ZIP  TAR.GZ
gg/scripts-eval

3754239e43 · eval : support multiple dataset runs · Updated 2026-02-02 22:34:25 +02:00
248
23
 ZIP  TAR.GZ
gg/compare-mlx

5b01d8575d · examples : add compare-mlx · Updated 2026-01-31 09:57:35 +02:00
53
1
 ZIP  TAR.GZ
gg/ngram-mod

6c8a04576e · experiments · Updated 2026-01-28 09:45:07 +02:00
104
29
 ZIP  TAR.GZ
gg/quant-manual-overrides

8b407e3978 · quant : manual overrides of tensor types take precedence · Updated 2026-01-20 11:20:24 +02:00
168
1
 ZIP  TAR.GZ
gg/winget-update

3bfbbcc5fc · winget : update komac version · Updated 2026-01-18 10:29:03 +02:00
178
1
 ZIP  TAR.GZ
gg/kv-mask-opt-verify

e2751545b9 · cont : inline verification · Updated 2026-01-17 14:33:07 +02:00
190
5
 ZIP  TAR.GZ
b7739

36f0132464 · CUDA: Factor out and re-use block_reduce function (#18785) · Updated 2026-01-15 04:44:54 +02:00
209
0
 Included
 ZIP  TAR.GZ
gg/fit-params-ngl

60864997fe · fit-params : print signed int for -ngl param · Updated 2026-01-14 19:59:23 +02:00
212
1
 ZIP  TAR.GZ
xsn/lora_keep_track

5292965711 · Merge branch 'master' into xsn/lora_keep_track · Updated 2026-01-13 14:44:22 +02:00
226
4
 ZIP  TAR.GZ
gg/webui-bs-send-false

c1c42f1544 · webui : send both backend_sampling == false/true · Updated 2026-01-12 15:19:23 +02:00
235
1
 ZIP  TAR.GZ
pr/18490

08b5d956fc · minor : std::unordered_set over std::set · Updated 2026-01-12 13:35:25 +02:00
365
3
 ZIP  TAR.GZ
gg/server-refactor

4a2751258a · server : simplify prompt state transition branches · Updated 2026-01-09 17:46:03 +02:00
264
11
 ZIP  TAR.GZ
copilot/sub-pr-18695

0fca4308f7 · Initial plan · Updated 2026-01-08 17:16:59 +02:00
274
2
 ZIP  TAR.GZ
revert-18624-rauletorresc-patch-11

d23c2899c8 · Revert "CANN: Rename get_env to get_env_as_lowercase (#18624)" · Updated 2026-01-07 04:31:28 +02:00
295
1
 ZIP  TAR.GZ
pr/18626

091d98e2c5 · rpc : use std::unique_ptr for the message_queue · Updated 2026-01-06 15:32:01 +02:00
313
2
 ZIP  TAR.GZ